Enter opens the highlighted result. Esc closes.

GPT-4.1 vs GPT-4.1 Mini

GPT-4.1 leads GPT-4.1 Mini on the Artificial Analysis Intelligence Index, 12.7 to 10.2, and GPT-4.1 Mini costs 5.0x less per output token ($1.60 vs $8.00 per million). Updated October 22, 2026; 84 benchmarks have a result for both.

Replace GPT-4.1 Replace GPT-4.1 Mini
GPT-4.1OpenAI
Coding
No data
Overall
36.5
Output $/M
$8.00
70
GPT-4.1 MiniOpenAI
Coding
No data
Overall
31.9
Output $/M
$1.60
14
vs boards won of 84 shared

GPT-4.1 or GPT-4.1 Mini: which to pick

Neither model has a coding score yet, so the two cannot be ranked on coding.

Pick GPT-4.1 for a lower cost per solved task ($0.37 against $1.818) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Model AGPT-4.1OpenAINot benchmarkedNo coding benchmark$0.37 per solved taskModel BGPT-4.1 MiniOpenAINot benchmarkedNo coding benchmark$1.818 per solved task
Shared results
84
GPT-4.1 only
8
GPT-4.1 Mini only
2
Like-for-like categories
8 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

At a glance

Coding index
GPT-4.1 not benchmarked, GPT-4.1 Mini not benchmarked.
Widest category
General, 7.3 points apart on average over 30 shared benchmarks.
Widest single gap
Long context reasoning (AA-LCR): GPT-4.1 68.3% against GPT-4.1 Mini 44.0%, 24.3 points apart on a 0 to 100 scale.
Output price
GPT-4.1 $8.00 against GPT-4.1 Mini $1.60 per million output tokens, 5.0x apart.
Context window
Both take 1.05M tokens.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
CategoryGPT-4.1BarsGPT-4.1 MiniTies
Coding62
Intelligence20
Agentic work11
Reasoning122
Math28
Knowledge120
Web design60
General291
All shared boards7014
CodingLike-for-likeSix of these boards feed the Vibe Coding Index62
Coding benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
Aider polyglot52.4%32.4%GPT-4.1
SWE-bench Verified39.6%23.9%GPT-4.1
SWE-bench Multimodal31.1%Not measuredOnly GPT-4.1 measured
AA Coding IndexNot measured20.2Only GPT-4.1 Mini measured
LiveCodeBench (Vals AI)54.7%58.2%GPT-4.1 Mini
LiveCodeBench (Artificial Analysis run)45.7%48.3%GPT-4.1 Mini
Terminal-Bench Hard (Artificial Analysis run)13.6%7.6%GPT-4.1
WeirdML39.0%37.6%GPT-4.1
ALE-Bench558.1Not measuredOnly GPT-4.1 measured
LMArena Text: coding13901367GPT-4.1
LMArena Text: software and IT13911360GPT-4.1
SciCode4.6%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 27 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
AA Intelligence Index12.710.2GPT-4.1
Epoch Capabilities Index136.7134.9GPT-4.1
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
Agentic work benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
τ²-Bench Telecom47.1%52.9%GPT-4.1 Mini
Berkeley Function Calling Leaderboard (BFCL)54.0%50.4%GPT-4.1
BrowseComp-Plus36.4%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 38 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index122
Reasoning benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
GPQA Diamond65.4%67.9%GPT-4.1 Mini
MMMU Pro (Vals AI)72.4%70.5%GPT-4.1
GPQA Diamond (Artificial Analysis run)66.6%66.4%GPT-4.1
Humanity's Last Exam (Artificial Analysis run)4.2%5.0%GPT-4.1 Mini
GPQA Diamond (Epoch AI run)66.9%65.8%GPT-4.1
ARC-AGI5.5%3.5%GPT-4.1
ARC-AGI-20.4%0.0%GPT-4.1
SimpleBench27.0%Not measuredOnly GPT-4.1 measured
Chess puzzles3.0%1.0%GPT-4.1
Mystery game puzzlesNot measured7.0%Only GPT-4.1 Mini measured
LMArena Text: hard prompts13841349GPT-4.1
LMArena Text: expert13641338GPT-4.1
LMArena Text: hard prompts in English13931362GPT-4.1
LMArena Vision: diagrams12151182GPT-4.1
LMArena Vision: homework12481214GPT-4.1
Kagi LLM Benchmark52.3%48.6%GPT-4.1
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index28
Math benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
AIME39.6%49.4%GPT-4.1 Mini
MATH 500 (Vals AI)87.2%88.0%GPT-4.1 Mini
MGSM (Vals AI)87.7%87.8%GPT-4.1 Mini
AA Math Index34.746.3GPT-4.1 Mini
AIME 2025 (Artificial Analysis run)34.7%46.3%GPT-4.1 Mini
OTIS Mock AIME38.3%44.7%GPT-4.1 Mini
FrontierMath, tiers 1 to 36.0%6.7%GPT-4.1 Mini
MATH level 583.0%87.3%GPT-4.1 Mini
LMArena Text: math13691343GPT-4.1
LMArena Text: mathematical work13601347GPT-4.1
Neither model has a result on the other 3 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index120
Knowledge benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
MMLU Pro80.5%77.2%GPT-4.1
LegalBench (Vals AI)83.1%78.0%GPT-4.1
CaseLaw (Vals AI)69.9%Not measuredOnly GPT-4.1 measured
CorpFin (Vals AI)63.0%57.9%GPT-4.1
TaxEval (Vals AI)75.1%71.9%GPT-4.1
MortgageTax (Vals AI)65.9%65.5%GPT-4.1
MedQA (Vals AI)91.2%84.6%GPT-4.1
MMLU Pro (Artificial Analysis run)80.6%78.1%GPT-4.1
SimpleQA Verified31.1%12.7%GPT-4.1
GeoBench72.0%Not measuredOnly GPT-4.1 measured
LMArena Text: science13821328GPT-4.1
LMArena Text: medicine and healthcare13791324GPT-4.1
LMArena Text: legal and government13991343GPT-4.1
LMArena Text: business and finance13691322GPT-4.1
FACTS Benchmark Suite45.8%Not measuredOnly GPT-4.1 measured
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index60
Web design benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
Design Arena: websites1038997GPT-4.1
Design Arena: UI components997958GPT-4.1
Design Arena: game dev10791070GPT-4.1
Design Arena: data viz11041034GPT-4.1
Design Arena: 3D849836GPT-4.1
Design Arena: all code categories1025993GPT-4.1
Neither model has a result on the other 3 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index291
General benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
IFBench43.0%38.3%GPT-4.1
Long context reasoning (AA-LCR)68.3%44.0%GPT-4.1
DTBench68.3%68.8%GPT-4.1 Mini
LMCA25.6%21.1%GPT-4.1
Fiction.LiveBench63.9%44.4%GPT-4.1
LMArena Text13831341GPT-4.1
LMArena Text: instruction following13671333GPT-4.1
LMArena Text: creative writing13631299GPT-4.1
LMArena Vision12101181GPT-4.1
LMArena Text: English13921356GPT-4.1
LMArena Text: non-English13701318GPT-4.1
LMArena Text: Chinese13821329GPT-4.1
LMArena Text: German13811350GPT-4.1
LMArena Text: Japanese13191290GPT-4.1
LMArena Text: Korean13381298GPT-4.1
LMArena Text: French13821358GPT-4.1
LMArena Text: Spanish13761319GPT-4.1
LMArena Text: Russian13771324GPT-4.1
LMArena Text: Polish13891326GPT-4.1
LMArena Text: multi-turn13971354GPT-4.1
LMArena Text: longer queries13851344GPT-4.1
LMArena Text: writing and language13711319GPT-4.1
LMArena Text: entertainment and media13651300GPT-4.1
LMArena Vision: English12091191GPT-4.1
LMArena Vision: Chinese12261186GPT-4.1
LMArena Vision: reading text12181188GPT-4.1
LMArena Vision: humor11961182GPT-4.1
LMArena Vision: captioning12071174GPT-4.1
LMArena Vision: recognizing things12081187GPT-4.1
LMArena Vision: creative writing12101182GPT-4.1
Neither model has a result on the other 16 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for GPT-4.1 and GPT-4.1 Mini
BenchmarkGPT-4.1GPT-4.1 MiniLeader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

GPT-4.1$0.0060Fits in one request
GPT-4.1 Mini$0.0012Fits in one request

GPT-4.1 Mini costs less

Repository review

50K input + 3K output tokens

GPT-4.1$0.124Fits in one request
GPT-4.1 Mini$0.025Fits in one request

GPT-4.1 Mini costs less

Agent loop

200K input + 10K output tokens

GPT-4.1$0.480Fits in one request
GPT-4.1 Mini$0.096Fits in one request

GPT-4.1 Mini costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of GPT-4.1 and GPT-4.1 Mini
SpecificationOpenAI GPT-4.1OpenAI GPT-4.1 Mini
MakerOpenAIOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedApril 14, 2025April 14, 2025
Context window1.05M1.05M
Input $/Mtok$2.00$0.40
Output $/Mtok$8.00$1.60
Coding indexNot benchmarkedNot benchmarked
Independent measurements behind it00
Cost per solved task$0.37$1.818
SourceOpenRouter listingOpenRouter listing

Questions

Is GPT-4.1 better than GPT-4.1 Mini for coding?

Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 for a lower cost per solved task ($0.37 against $1.818) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.

Which is cheaper, GPT-4.1 or GPT-4.1 Mini?

GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; GPT-4.1 Mini costs $0.40 and $1.60. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and GPT-4.1 Mini $1.818.

Which has the bigger context window, GPT-4.1 or GPT-4.1 Mini?

Neither: both take 1.05M tokens.

How many benchmarks is the GPT-4.1 vs GPT-4.1 Mini comparison based on?

84 benchmarks have a result for both models as of October 22, 2026. GPT-4.1's coding index rests on 0 independent benchmarks and GPT-4.1 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.

Compare next